Relative survival and excess hazard models

Measure what a cancer does to a population when nobody can tell you the cause of death.

Taught by

Sara Ekberg, PhD

Associate Director of Applied Biostatistics

Over 15 years of experience in register-based epidemiological research, and a lecturer with a passion for teaching statistics to non-statisticians.

Research cancer survival · survivorship · register-based research · teaching

PhD in Medical Sciences, Karolinska Institutet, 2021

Michael Crowther, PhD

CEO & Director of Statistical Methodology

Formerly Associate Professor of Biostatistics at the University of Leicester, and the author of the merlin framework.

Research survival analysis · joint models · multi-state models · statistical software

PhD in Medical Statistics, University of Leicester, 2014

Register your interest

What you will be able to do

• Say what net survival estimates, why it is not cause-specific survival, and what assumption buys it
• Attach a population life table to a cohort on attained age, sex and year, and recognise the merge failures that produce a plausible wrong answer
• Fit an excess hazard model with merlin's bhazard(), read excess hazard ratios and net survival out of it, and choose stexcess instead when the reference rate has to be modelled
• Age-standardise a comparison between populations, and report crude probabilities of death alongside net survival because only one of them is about a patient

Before you start

• Take first: Survival analysis
• Helps to have done: Flexible parametric survival models

Curriculum

13 steps: 11 lectures, 1 practical and 1 quiz.

Provisional — this course is still being written, and the outline will change.

Week 1 · what you are estimating

• 01WatchNet survival, relative survival, and cause-specific survival24 min
• 02WatchThe excess hazard, and where the expected rate comes from24 min

Week 2 · expected mortality and the life table

Opens 7 days after you start.

• 03WatchWhat is in a life table22 min
• 04WatchMerging on age, sex and year28 min
• 05WatchSplitting follow-up, and expected survival24 min
• 06PracticalPractical · expected mortality, and the ratio it gives you50 min
• 07QuizChecking what you have understood10 min

Week 3 · the excess hazard model

Opens 14 days after you start.

• 08WatchFitting an excess hazard model24 min
• 09WatchReading the output26 min
• 10WatchA modelled reference rate, when there is no life table28 min

Week 4 · reporting

Opens 21 days after you start.

• 11WatchAge standardisation, and comparing two populations26 min
• 12WatchCrude probabilities of death26 min
• 13ReadWhat a net survival estimate is about22 min